> ## Documentation Index
> Fetch the complete documentation index at: https://docs.portkey.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Bring Your Own LLM

> Integrate your privately hosted LLMs with Prisma AIRS AI Gateway for unified management, observability, and reliability.

The AI Gateway's Bring Your Own LLM feature allows you to seamlessly integrate privately hosted language models into your AI infrastructure. This powerful capability enables unified management of both private and commercial LLMs through a consistent interface while leveraging the AI Gateway's comprehensive suite of observability and reliability features.

## Key Benefits

* **Unified API Access**: Manage private and commercial LLMs through a single, consistent interface
* **Enhanced Reliability**: Leverage the AI Gateway's fallbacks, retries, and load balancing for your private deployments
* **Comprehensive Monitoring**: Track performance, usage, and costs alongside your commercial LLM usage
* **Simplified Access Control**: Manage team-specific permissions and usage limits
* **Secure Credential Management**: Protect sensitive authentication details through the AI Gateway's secure vault

## Integration Options

<Note>
  **Prerequisites**

  Your private LLM must implement an API specification compatible with one of the AI Gateway's [supported providers](/docs/aigw/integrations/llms) (e.g., OpenAI's `/chat/completions`, Anthropic's `/messages`, etc.).
</Note>

The AI Gateway offers two primary methods to integrate your private LLMs:

1. **Using Model Catalog**: Store your deployment details securely in the AI Gateway's Model Catalog
2. **Direct Integration**: Pass deployment details in your requests without storing them

### Option 1: Using Model Catalog

#### Step 1: Add Your Private LLM to Model Catalog

Navigate to [**Model Catalog → Add Provider**](https://stratacloudmanager.paloaltonetworks.com/) in Strata Cloud Manager.

1. Click **"Add Provider"** and enable the **"Local/Privately hosted provider"** toggle
2. Configure your deployment:
   * Select the matching provider API specification (typically `OpenAI`)
   * Enter your model's base URL in the `Custom Host` field
   * Add required authentication headers and their values
3. Name your provider (e.g., `my-private-llm`)
4. Click **"Create"** to save your configuration

#### Step 2: Use Your Provider in Requests

After adding your provider to the Model Catalog, you can use it in your applications:

<CodeGroup>
  ```sh cURL theme={"system"}
  curl https://aigw.portkey.ai/v1/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $PORTKEY_API_KEY" \
    -d '{
      "model": "@my-private-llm/YOUR_MODEL_NAME",
      "messages": [
        { "role": "user", "content": "Explain quantum computing in simple terms" }
      ]
    }'
  ```
</CodeGroup>

### Option 2: Direct Integration Without Model Catalog

If you prefer not to store your private LLM details in the AI Gateway's Model Catalog, you can pass them directly in your API requests:

<CodeGroup>
  ```sh cURL theme={"system"}
  curl https://aigw.portkey.ai/v1/chat/completions \
    -H "Content-Type: application/json" \
    -H "x-portkey-api-key: $PORTKEY_API_KEY" \
    -H "x-portkey-provider: openai" \
    -H "x-portkey-custom-host: https://your-llm-server.com/v1" \
    -H "Authorization: Bearer YOUR_AUTH_TOKEN" \
    -H "x-portkey-forward-headers: Authorization" \
    -d '{
      "model": "YOUR_MODEL_NAME",
      "messages": [
        { "role": "user", "content": "Explain quantum computing in simple terms" }
      ]
    }'
  ```
</CodeGroup>

<Note>
  The `custom_host` must include the API version path (e.g., `/v1/`). The AI Gateway will automatically append the endpoint path (`/chat/completions`, `/completions`, or `/embeddings`).
</Note>

<Info>
  The AI Gateway blocks requests to private and reserved IP ranges by default. If your private LLM runs on an internal network IP, see [Custom hosts](/docs/aigw/product/ai-gateway/custom-hosts) for blocked patterns and how to allowlist specific hosts.
</Info>

***

## Securely Forwarding Sensitive Headers

For headers containing sensitive information that shouldn't be logged or processed by the AI Gateway, use the `forward_headers` parameter to pass them directly to your private LLM:

<Tabs>
  <Tab title="cURL">
    ```sh theme={"system"}
    curl https://aigw.portkey.ai/v1/chat/completions \
      -H "Content-Type: application/json" \
      -H "x-portkey-api-key: $PORTKEY_API_KEY" \
      -H "x-portkey-provider: openai" \
      -H "x-portkey-custom-host: https://your-llm-server.com/v1" \
      -H "Authorization: Bearer sk_live_xxxxx" \
      -H "x-api-key: sensitive-key-value" \
      -H "x-org-id: org-12345" \
      -H "x-portkey-forward-headers: Authorization, x-api-key, x-org-id" \
      -d '{
        "model": "YOUR_MODEL_NAME",
        "messages": [{ "role": "user", "content": "Hello!" }]
      }'
    ```
  </Tab>
</Tabs>

### Using Forward Headers in Gateway Configs

You can also specify `forward_headers` in your Gateway Config for consistent header forwarding:

```json theme={"system"}
{
  "strategy": { "mode": "fallback" },
  "targets": [
    {
      "provider": "openai",
      "custom_host": "https://your-private-llm.com/v1",
      "forward_headers": ["Authorization", "x-api-key", "x-custom-token"]
    },
    {
      "provider": "openai",
      "api_key": "sk-xxxxx"  // Fallback to commercial provider
    }
  ]
}
```

## Advanced Features

### Using Private LLMs with Gateway Configs

Private LLMs work seamlessly with all AI Gateway features. Some common use cases:

* **Load Balancing**: Distribute traffic across multiple private LLM instances
* **Fallbacks**: Set up automatic failover between private and commercial LLMs
* **Conditional Routing**: Route requests to different LLMs based on metadata

```json theme={"system"}
{
    "strategy": {
        "mode": "fallback"
    },
    "targets": [
        {
            "provider": "openai",
            "custom_host": "http://PRIVATE_LLM/v1",
            "forward_headers": ["Authorization"]
        },
        {
            "provider":"@openai-key"
        }
    ]
}
```

Learn more about [Gateway Configs](/docs/aigw/product/ai-gateway/configs).

***

## Monitoring and Analytics

The AI Gateway provides comprehensive observability for your private LLM deployments, just like it does for commercial providers:

* **Log Analysis**: View detailed request and response logs
* **Performance Metrics**: Track latency, token usage, and error rates
* **User Attribution**: Associate requests with specific users via metadata

***

## Troubleshooting

| Issue                   | Possible Causes                                     | Solutions                                                                      |
| ----------------------- | --------------------------------------------------- | ------------------------------------------------------------------------------ |
| Connection Errors       | Incorrect URL, network issues, firewall rules       | Verify URL format, check network connectivity, confirm firewall allows traffic |
| Authentication Failures | Invalid credentials, incorrect header format        | Check credentials, ensure headers are correctly formatted and forwarded        |
| Timeout Errors          | LLM server overloaded, request too complex          | Adjust timeout settings, implement load balancing, simplify requests           |
| Inconsistent Responses  | Different model versions, configuration differences | Standardize model versions, document expected behavior differences             |

## FAQs

<AccordionGroup>
  <Accordion title="Can I use any private LLM with the AI Gateway?">
    Yes, as long as it implements an API specification compatible with one of the AI Gateway's supported providers (OpenAI, Anthropic, etc.). The model should accept requests and return responses in the format expected by that provider.
  </Accordion>

  <Accordion title="How do I handle multiple deployment endpoints?">
    You have two options:

    1. Create separate integration for each endpoint
    2. Use Gateway Configs with load balancing to distribute traffic across multiple endpoints
  </Accordion>

  <Accordion title="Are there any request volume limitations?">
    The AI Gateway itself doesn't impose specific request volume limitations for private LLMs. Your throughput will be limited only by your private LLM deployment's capabilities and any rate limits you configure in the AI Gateway.
  </Accordion>

  <Accordion title="Can I use different models with the same private deployment?">
    Yes, you can specify different model names in your requests as long as your private LLM deployment supports them. The model name is passed through to your deployment.
  </Accordion>

  <Accordion title="Can I mix private and commercial LLMs in the same application?">
    Absolutely! One of the AI Gateway's key benefits is the ability to manage both private and commercial LLMs through a unified interface. You can even set up fallbacks between them or route requests conditionally.
  </Accordion>
</AccordionGroup>

***

## Next Steps

Explore these related resources to get the most out of your private LLM integration:

<CardGroup cols={2}>
  <Card title="Universal API" icon="globe" href="/docs/aigw/product/ai-gateway/universal-api" />

  <Card title="Adding Metadata" icon="tags" href="/docs/aigw/product/observability/metadata" />

  <Card title="Gateway Configs" icon="sliders" href="/docs/aigw/product/ai-gateway/configs" />

  <Card title="Request Tracing" icon="route" href="/docs/aigw/product/observability/traces" />
</CardGroup>


## Related topics

- [Custom hosts](/docs/aigw/product/ai-gateway/custom-hosts.md)
- [Bring Your Own Guardrails](/docs/aigw/integrations/guardrails/bring-your-own-guardrails.md)
- [Bring Your own Agents](/docs/aigw/integrations/agents/bring-your-own-agents.md)
- [Bring Your Own Auth](/docs/aigw/product/mcp-gateway/authentication/external-oauth.md)
- [Guardrails](/docs/aigw/product/guardrails.md)